Upload 17 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "EchoForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.01,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 384,
+  "hidden_act": "relu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 32,
+  "model_type": "echo",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 28,
+  "optimizer_type": "adafactor",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690364eac7b2987780223d4cd3baa9e5694d7eecb7f6539f700a0211679137d9
+size 4969935136

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bbb31b26bf23fc006055b2196a42bac1a9278a61eb8ad9e3416eba492faccf0
+size 2900508248

model.safetensors.index.json

@@ -0,0 +1,361 @@
+{
+  "metadata": {
+    "total_size": 7870402560
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067949f756434660c2909fb0ebee32ace1da420e252458625d7126afb120cce1
+size 10411211

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378bcb71fdead11bd76077ba39a72555c531f86af08d0e1cff5c52aa8a9bcf2f
+size 14391

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6371ad05a88ac0abdc69e4fab00abdbc2cd81721a7894f1e422ab0fd12442f7e
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,741 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.012497188132670149,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.4994376265340298e-05,
+      "grad_norm": 22.25,
+      "learning_rate": 0.0008,
+      "loss": 12.4316,
+      "step": 1
+    },
+    {
+      "epoch": 0.00012497188132670149,
+      "grad_norm": 4.40625,
+      "learning_rate": 0.0007999840035991902,
+      "loss": 13.3525,
+      "step": 5
+    },
+    {
+      "epoch": 0.00024994376265340297,
+      "grad_norm": 4.5,
+      "learning_rate": 0.000799964008098178,
+      "loss": 14.8491,
+      "step": 10
+    },
+    {
+      "epoch": 0.00037491564398010446,
+      "grad_norm": 6.84375,
+      "learning_rate": 0.0007999440125971656,
+      "loss": 8.8491,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004998875253068059,
+      "grad_norm": 3.75,
+      "learning_rate": 0.0007999240170961534,
+      "loss": 7.9633,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006248594066335074,
+      "grad_norm": 4.75,
+      "learning_rate": 0.0007999040215951412,
+      "loss": 7.787,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007498312879602089,
+      "grad_norm": 15.3125,
+      "learning_rate": 0.0007998840260941289,
+      "loss": 7.6196,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008748031692869104,
+      "grad_norm": 3.03125,
+      "learning_rate": 0.0007998640305931166,
+      "loss": 7.453,
+      "step": 35
+    },
+    {
+      "epoch": 0.0009997750506136119,
+      "grad_norm": 3.921875,
+      "learning_rate": 0.0007998440350921043,
+      "loss": 7.3384,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011247469319403134,
+      "grad_norm": 3.203125,
+      "learning_rate": 0.000799824039591092,
+      "loss": 7.2074,
+      "step": 45
+    },
+    {
+      "epoch": 0.0012497188132670149,
+      "grad_norm": 3.28125,
+      "learning_rate": 0.0007998040440900798,
+      "loss": 7.1685,
+      "step": 50
+    },
+    {
+      "epoch": 0.0013746906945937163,
+      "grad_norm": 3.578125,
+      "learning_rate": 0.0007997840485890674,
+      "loss": 7.2311,
+      "step": 55
+    },
+    {
+      "epoch": 0.0014996625759204178,
+      "grad_norm": 7.28125,
+      "learning_rate": 0.0007997640530880552,
+      "loss": 7.1694,
+      "step": 60
+    },
+    {
+      "epoch": 0.0016246344572471193,
+      "grad_norm": 3.0,
+      "learning_rate": 0.0007997440575870429,
+      "loss": 7.1179,
+      "step": 65
+    },
+    {
+      "epoch": 0.0017496063385738208,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.0007997240620860307,
+      "loss": 7.1143,
+      "step": 70
+    },
+    {
+      "epoch": 0.0018745782199005223,
+      "grad_norm": 3.46875,
+      "learning_rate": 0.0007997040665850185,
+      "loss": 7.0387,
+      "step": 75
+    },
+    {
+      "epoch": 0.0019995501012272238,
+      "grad_norm": 3.484375,
+      "learning_rate": 0.0007996840710840061,
+      "loss": 6.825,
+      "step": 80
+    },
+    {
+      "epoch": 0.0021245219825539252,
+      "grad_norm": 2.859375,
+      "learning_rate": 0.0007996640755829939,
+      "loss": 6.7811,
+      "step": 85
+    },
+    {
+      "epoch": 0.0022494938638806267,
+      "grad_norm": 2.640625,
+      "learning_rate": 0.0007996440800819816,
+      "loss": 6.821,
+      "step": 90
+    },
+    {
+      "epoch": 0.0023744657452073282,
+      "grad_norm": 3.0,
+      "learning_rate": 0.0007996240845809693,
+      "loss": 6.7552,
+      "step": 95
+    },
+    {
+      "epoch": 0.0024994376265340297,
+      "grad_norm": 3.953125,
+      "learning_rate": 0.000799604089079957,
+      "loss": 6.7139,
+      "step": 100
+    },
+    {
+      "epoch": 0.002624409507860731,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.0007995840935789447,
+      "loss": 6.7687,
+      "step": 105
+    },
+    {
+      "epoch": 0.0027493813891874327,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.0007995640980779325,
+      "loss": 6.6156,
+      "step": 110
+    },
+    {
+      "epoch": 0.002874353270514134,
+      "grad_norm": 4.28125,
+      "learning_rate": 0.0007995441025769203,
+      "loss": 6.5183,
+      "step": 115
+    },
+    {
+      "epoch": 0.0029993251518408356,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.000799524107075908,
+      "loss": 6.5023,
+      "step": 120
+    },
+    {
+      "epoch": 0.003124297033167537,
+      "grad_norm": 3.0,
+      "learning_rate": 0.0007995041115748957,
+      "loss": 6.3342,
+      "step": 125
+    },
+    {
+      "epoch": 0.0032492689144942386,
+      "grad_norm": 3.296875,
+      "learning_rate": 0.0007994841160738834,
+      "loss": 6.416,
+      "step": 130
+    },
+    {
+      "epoch": 0.00337424079582094,
+      "grad_norm": 3.90625,
+      "learning_rate": 0.0007994641205728712,
+      "loss": 6.3348,
+      "step": 135
+    },
+    {
+      "epoch": 0.0034992126771476416,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.0007994441250718589,
+      "loss": 6.3827,
+      "step": 140
+    },
+    {
+      "epoch": 0.003624184558474343,
+      "grad_norm": 2.5,
+      "learning_rate": 0.0007994241295708465,
+      "loss": 6.4047,
+      "step": 145
+    },
+    {
+      "epoch": 0.0037491564398010446,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.0007994041340698343,
+      "loss": 6.1781,
+      "step": 150
+    },
+    {
+      "epoch": 0.003874128321127746,
+      "grad_norm": 3.375,
+      "learning_rate": 0.000799384138568822,
+      "loss": 6.2532,
+      "step": 155
+    },
+    {
+      "epoch": 0.0039991002024544475,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.0007993641430678099,
+      "loss": 6.2372,
+      "step": 160
+    },
+    {
+      "epoch": 0.004124072083781149,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.0007993441475667975,
+      "loss": 6.0455,
+      "step": 165
+    },
+    {
+      "epoch": 0.0042490439651078505,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.0007993241520657852,
+      "loss": 6.1694,
+      "step": 170
+    },
+    {
+      "epoch": 0.004374015846434552,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.000799304156564773,
+      "loss": 6.045,
+      "step": 175
+    },
+    {
+      "epoch": 0.0044989877277612535,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.0007992841610637607,
+      "loss": 6.0104,
+      "step": 180
+    },
+    {
+      "epoch": 0.004623959609087955,
+      "grad_norm": 1.796875,
+      "learning_rate": 0.0007992641655627485,
+      "loss": 5.9327,
+      "step": 185
+    },
+    {
+      "epoch": 0.0047489314904146564,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.0007992441700617361,
+      "loss": 5.9164,
+      "step": 190
+    },
+    {
+      "epoch": 0.004873903371741358,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0007992241745607238,
+      "loss": 5.9775,
+      "step": 195
+    },
+    {
+      "epoch": 0.004998875253068059,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.0007992041790597116,
+      "loss": 5.6958,
+      "step": 200
+    },
+    {
+      "epoch": 0.005123847134394761,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.0007991841835586994,
+      "loss": 5.8286,
+      "step": 205
+    },
+    {
+      "epoch": 0.005248819015721462,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.000799164188057687,
+      "loss": 5.7053,
+      "step": 210
+    },
+    {
+      "epoch": 0.005373790897048164,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.0007991441925566748,
+      "loss": 5.725,
+      "step": 215
+    },
+    {
+      "epoch": 0.005498762778374865,
+      "grad_norm": 1.875,
+      "learning_rate": 0.0007991241970556625,
+      "loss": 5.6576,
+      "step": 220
+    },
+    {
+      "epoch": 0.005623734659701567,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.0007991042015546503,
+      "loss": 5.7389,
+      "step": 225
+    },
+    {
+      "epoch": 0.005748706541028268,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.000799084206053638,
+      "loss": 5.4624,
+      "step": 230
+    },
+    {
+      "epoch": 0.00587367842235497,
+      "grad_norm": 2.625,
+      "learning_rate": 0.0007990642105526257,
+      "loss": 5.6441,
+      "step": 235
+    },
+    {
+      "epoch": 0.005998650303681671,
+      "grad_norm": 2.5,
+      "learning_rate": 0.0007990442150516134,
+      "loss": 5.552,
+      "step": 240
+    },
+    {
+      "epoch": 0.006123622185008373,
+      "grad_norm": 1.640625,
+      "learning_rate": 0.0007990242195506011,
+      "loss": 5.3983,
+      "step": 245
+    },
+    {
+      "epoch": 0.006248594066335074,
+      "grad_norm": 2.640625,
+      "learning_rate": 0.000799004224049589,
+      "loss": 5.3757,
+      "step": 250
+    },
+    {
+      "epoch": 0.006373565947661776,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0007989842285485766,
+      "loss": 5.4723,
+      "step": 255
+    },
+    {
+      "epoch": 0.006498537828988477,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0007989642330475643,
+      "loss": 5.301,
+      "step": 260
+    },
+    {
+      "epoch": 0.006623509710315179,
+      "grad_norm": 1.90625,
+      "learning_rate": 0.0007989442375465521,
+      "loss": 5.4499,
+      "step": 265
+    },
+    {
+      "epoch": 0.00674848159164188,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.0007989242420455398,
+      "loss": 5.5597,
+      "step": 270
+    },
+    {
+      "epoch": 0.006873453472968582,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0007989042465445275,
+      "loss": 5.2123,
+      "step": 275
+    },
+    {
+      "epoch": 0.006998425354295283,
+      "grad_norm": 1.71875,
+      "learning_rate": 0.0007988842510435152,
+      "loss": 5.3393,
+      "step": 280
+    },
+    {
+      "epoch": 0.007123397235621985,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.000798864255542503,
+      "loss": 5.2593,
+      "step": 285
+    },
+    {
+      "epoch": 0.007248369116948686,
+      "grad_norm": 2.125,
+      "learning_rate": 0.0007988442600414907,
+      "loss": 5.2776,
+      "step": 290
+    },
+    {
+      "epoch": 0.007373340998275388,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.0007988242645404785,
+      "loss": 5.2529,
+      "step": 295
+    },
+    {
+      "epoch": 0.007498312879602089,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.0007988042690394662,
+      "loss": 5.0664,
+      "step": 300
+    },
+    {
+      "epoch": 0.007623284760928791,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.0007987842735384539,
+      "loss": 5.3028,
+      "step": 305
+    },
+    {
+      "epoch": 0.007748256642255492,
+      "grad_norm": 1.7578125,
+      "learning_rate": 0.0007987642780374416,
+      "loss": 5.2152,
+      "step": 310
+    },
+    {
+      "epoch": 0.007873228523582194,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.0007987442825364294,
+      "loss": 4.97,
+      "step": 315
+    },
+    {
+      "epoch": 0.007998200404908895,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.000798724287035417,
+      "loss": 5.1328,
+      "step": 320
+    },
+    {
+      "epoch": 0.008123172286235597,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.0007987042915344048,
+      "loss": 5.0475,
+      "step": 325
+    },
+    {
+      "epoch": 0.008248144167562298,
+      "grad_norm": 1.78125,
+      "learning_rate": 0.0007986842960333925,
+      "loss": 5.009,
+      "step": 330
+    },
+    {
+      "epoch": 0.008373116048889,
+      "grad_norm": 1.90625,
+      "learning_rate": 0.0007986643005323803,
+      "loss": 5.0827,
+      "step": 335
+    },
+    {
+      "epoch": 0.008498087930215701,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.000798644305031368,
+      "loss": 5.0896,
+      "step": 340
+    },
+    {
+      "epoch": 0.008623059811542403,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.0007986243095303557,
+      "loss": 4.9185,
+      "step": 345
+    },
+    {
+      "epoch": 0.008748031692869104,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0007986043140293435,
+      "loss": 5.0279,
+      "step": 350
+    },
+    {
+      "epoch": 0.008873003574195806,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.0007985843185283312,
+      "loss": 4.8811,
+      "step": 355
+    },
+    {
+      "epoch": 0.008997975455522507,
+      "grad_norm": 1.640625,
+      "learning_rate": 0.0007985643230273188,
+      "loss": 5.0377,
+      "step": 360
+    },
+    {
+      "epoch": 0.00912294733684921,
+      "grad_norm": 2.078125,
+      "learning_rate": 0.0007985443275263066,
+      "loss": 4.9903,
+      "step": 365
+    },
+    {
+      "epoch": 0.00924791921817591,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.0007985243320252943,
+      "loss": 4.8109,
+      "step": 370
+    },
+    {
+      "epoch": 0.009372891099502612,
+      "grad_norm": 1.859375,
+      "learning_rate": 0.0007985043365242821,
+      "loss": 4.8445,
+      "step": 375
+    },
+    {
+      "epoch": 0.009497862980829313,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0007984843410232698,
+      "loss": 4.887,
+      "step": 380
+    },
+    {
+      "epoch": 0.009622834862156015,
+      "grad_norm": 1.96875,
+      "learning_rate": 0.0007984643455222575,
+      "loss": 4.8373,
+      "step": 385
+    },
+    {
+      "epoch": 0.009747806743482716,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.0007984443500212453,
+      "loss": 4.8948,
+      "step": 390
+    },
+    {
+      "epoch": 0.009872778624809418,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.000798424354520233,
+      "loss": 4.9098,
+      "step": 395
+    },
+    {
+      "epoch": 0.009997750506136119,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.0007984043590192208,
+      "loss": 4.6948,
+      "step": 400
+    },
+    {
+      "epoch": 0.010122722387462821,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.0007983843635182084,
+      "loss": 4.7561,
+      "step": 405
+    },
+    {
+      "epoch": 0.010247694268789522,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0007983643680171961,
+      "loss": 4.6634,
+      "step": 410
+    },
+    {
+      "epoch": 0.010372666150116224,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.0007983443725161839,
+      "loss": 4.6339,
+      "step": 415
+    },
+    {
+      "epoch": 0.010497638031442925,
+      "grad_norm": 1.953125,
+      "learning_rate": 0.0007983243770151716,
+      "loss": 4.7292,
+      "step": 420
+    },
+    {
+      "epoch": 0.010622609912769627,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0007983043815141594,
+      "loss": 4.6211,
+      "step": 425
+    },
+    {
+      "epoch": 0.010747581794096328,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.0007982843860131471,
+      "loss": 4.6857,
+      "step": 430
+    },
+    {
+      "epoch": 0.01087255367542303,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.0007982643905121348,
+      "loss": 4.6335,
+      "step": 435
+    },
+    {
+      "epoch": 0.01099752555674973,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.0007982443950111226,
+      "loss": 4.7285,
+      "step": 440
+    },
+    {
+      "epoch": 0.011122497438076433,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.0007982243995101103,
+      "loss": 4.7707,
+      "step": 445
+    },
+    {
+      "epoch": 0.011247469319403134,
+      "grad_norm": 1.78125,
+      "learning_rate": 0.000798204404009098,
+      "loss": 4.6769,
+      "step": 450
+    },
+    {
+      "epoch": 0.011372441200729836,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.0007981844085080857,
+      "loss": 4.7311,
+      "step": 455
+    },
+    {
+      "epoch": 0.011497413082056537,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.0007981644130070734,
+      "loss": 4.6677,
+      "step": 460
+    },
+    {
+      "epoch": 0.011622384963383239,
+      "grad_norm": 1.328125,
+      "learning_rate": 0.0007981444175060612,
+      "loss": 4.6862,
+      "step": 465
+    },
+    {
+      "epoch": 0.01174735684470994,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.0007981244220050488,
+      "loss": 4.5674,
+      "step": 470
+    },
+    {
+      "epoch": 0.011872328726036642,
+      "grad_norm": 1.8671875,
+      "learning_rate": 0.0007981044265040366,
+      "loss": 4.5283,
+      "step": 475
+    },
+    {
+      "epoch": 0.011997300607363343,
+      "grad_norm": 1.625,
+      "learning_rate": 0.0007980844310030244,
+      "loss": 4.5966,
+      "step": 480
+    },
+    {
+      "epoch": 0.012122272488690045,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0007980644355020121,
+      "loss": 4.4785,
+      "step": 485
+    },
+    {
+      "epoch": 0.012247244370016746,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.0007980444400009999,
+      "loss": 4.5966,
+      "step": 490
+    },
+    {
+      "epoch": 0.012372216251343448,
+      "grad_norm": 1.8671875,
+      "learning_rate": 0.0007980244444999875,
+      "loss": 4.6428,
+      "step": 495
+    },
+    {
+      "epoch": 0.012497188132670149,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.0007980044489989753,
+      "loss": 4.5225,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200045,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2266079346688e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e49215338e18eaef6196903db1b15aee72f170b532bfd6357ab5bcd539e3efc
+size 5649